Jennifer Schmitz writes:
>> On 22 Oct 2024, at 18:21, Richard Sandiford
>> wrote:
>>
>> External email: Use caution opening links or attachments
>>
>>
>> Jennifer Schmitz writes:
>>> A common idiom in intrinsics loops is to have accumulator intrinsics
>>> in an unrolled loop with an accumula
> On 24 Oct 2024, at 11:28, Richard Sandiford wrote:
>
> External email: Use caution opening links or attachments
>
>
> Jennifer Schmitz writes:
>>> On 22 Oct 2024, at 18:21, Richard Sandiford
>>> wrote:
>>>
>>> External email: Use caution opening links or attachments
>>>
>>>
>>> Jennif
> On 22 Oct 2024, at 18:21, Richard Sandiford wrote:
>
> External email: Use caution opening links or attachments
>
>
> Jennifer Schmitz writes:
>> A common idiom in intrinsics loops is to have accumulator intrinsics
>> in an unrolled loop with an accumulator initialized to zero at the begin
Jennifer Schmitz writes:
> A common idiom in intrinsics loops is to have accumulator intrinsics
> in an unrolled loop with an accumulator initialized to zero at the beginning.
> Propagating the initial zero accumulator into the first iteration
> of the loop and simplifying the first accumulate ins
Ping.
Thanks,
Jennifer
> On 18 Oct 2024, at 09:30, Jennifer Schmitz wrote:
>
> A common idiom in intrinsics loops is to have accumulator intrinsics
> in an unrolled loop with an accumulator initialized to zero at the beginning.
> Propagating the initial zero accumulator into the first iteration
A common idiom in intrinsics loops is to have accumulator intrinsics
in an unrolled loop with an accumulator initialized to zero at the beginning.
Propagating the initial zero accumulator into the first iteration
of the loop and simplifying the first accumulate instruction is a
desirable transforma
